2026-04-17T16:33:37Z https://ipsj.ixsq.nii.ac.jp/oai

oai:ipsj.ixsq.nii.ac.jp:00218188 2025-01-19T15:14:19Z 1164:4061:10837:10917

Automatic Eating Stage Classification using ASMR videos Automatic Eating Stage Classification using ASMR videos Mari, Izumikawa Takafumi, Kawasaki Tadashi, Okoshi Jin, Nakazawa Mari, Izumikawa Takafumi, Kawasaki Tadashi, Okoshi Jin, Nakazawa 感覚・知覚 A balanced diet and an appropriate calorie intake are the keys to both preventing and treating type II diabetes. Meanwhile, widespread techniques such as manual food logs and food image captures have been posing burdens on those with diabetes and have made diet monitoring difficult to become part of one's routine. The ultimate aim of this study is to develop an earable device that monitors a volume of food intake automatically. However, an automatic food intake volume monitoring requires a detection of biting, chewing, and swallowing sounds with foods of various sizes and textures. The present research therefore attempted to classify an eating sound, collected from YouTube eating ASMR, into one of the following labels: bite/chew, swallow, or other. A CNN machine learning model using sound features as input achieved an accuracy of 86%. A balanced diet and an appropriate calorie intake are the keys to both preventing and treating type II diabetes. Meanwhile, widespread techniques such as manual food logs and food image captures have been posing burdens on those with diabetes and have made diet monitoring difficult to become part of one's routine. The ultimate aim of this study is to develop an earable device that monitors a volume of food intake automatically. However, an automatic food intake volume monitoring requires a detection of biting, chewing, and swallowing sounds with foods of various sizes and textures. The present research therefore attempted to classify an eating sound, collected from YouTube eating ASMR, into one of the following labels: bite/chew, swallow, or other. A CNN machine learning model using sound features as input achieved an accuracy of 86%. 情報処理学会 2022-05-30 eng technical report https://ipsj.ixsq.nii.ac.jp/records/218188 2188-8698 AA11838947 研究報告ユビキタスコンピューティングシステム（UBI） 2022-UBI-74 9 1 7 https://ipsj.ixsq.nii.ac.jp/record/218188/files/IPSJ-UBI22074009.pdf application/pdf 8.4 MB 2024-05-30